See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification

TL;DR

This paper introduces WS-DAN, a weakly supervised data augmentation network that uses attention maps to enhance fine-grained visual classification by focusing on discriminative object parts, leading to improved accuracy.

Contribution

The paper proposes a novel weakly supervised data augmentation method that leverages attention maps for more effective training in fine-grained classification tasks.

Findings

WS-DAN surpasses state-of-the-art methods on fine-grained datasets.

Attention-guided augmentation improves discriminative feature extraction.

The approach enhances model focus on relevant object parts.

Abstract

Data augmentation is usually adopted to increase the amount of training data, prevent overfitting and improve the performance of deep models. However, in practice, random data augmentation, such as random image cropping, is low-efficiency and might introduce many uncontrolled background noises. In this paper, we propose Weakly Supervised Data Augmentation Network (WS-DAN) to explore the potential of data augmentation. Specifically, for each training image, we first generate attention maps to represent the object's discriminative parts by weakly supervised learning. Next, we augment the image guided by these attention maps, including attention cropping and attention dropping. The proposed WS-DAN improves the classification accuracy in two folds. In the first stage, images can be seen better since more discriminative parts' features will be extracted. In the second stage, attention regions provide accurate location of object, which ensures our model to look at the object closer and further improve the performance. Comprehensive experiments in common fine-grained visual classification datasets show that our WS-DAN surpasses the state-of-the-art methods, which demonstrates its effectiveness.